Gorilla to Tidy Data: Cognitive Control and Motivated Reasoning

Data cleaning, data checks, and some preparations for further analyses.

# use groundhog to make code maximally reproducible
if (!require("groundhog", quietly = TRUE)) {
  install.packages("groundhog")
}
library("groundhog")

# use groundhog to install and load packages
pkgs <- c("here",         # System path management
          "tidyverse",    # ggplot, dplyr, %>%, and friends
          "tinytable"     # Lightweight package to create tables
          )

groundhog.library(pkgs, "2024-07-01")

Load the data

I have data from different versions of the tasks and questionnaires. The following code automatically loads them from the specified path and renames them with the task | questionnaire identifier.

# Define the path to stored raw data
raw_dir <- here("01_data", "raw") 

# List all CSV files in the folder
raw_files_list <- list.files(path = raw_dir, pattern = "*.csv", full.names = TRUE)

# Function to read a CSV file and assign it to a dataframe with the desired name
read_and_assign_simple <- function(file) {
  # Extract parts of the file name
  file_name <- basename(file)
  parts <- str_match(file_name, "data_exp_.*_(questionnaire|task)-(.*)\\.csv")
  task_or_questionnaire <- parts[2]
  identifier <- parts[3]
  
  # Create the new name
  new_name <- paste0("data_", task_or_questionnaire, "_", identifier)
  
  # Read the CSV file
  df <- read_csv(file)
  
  # Filter out rows where "Participant Private ID" is NA
  df <- df %>% filter(!is.na(`Participant Private ID`))
  
  # Assign the dataframe to the new name in the global environment
  assign(new_name, df, envir = .GlobalEnv)
}

# Apply the function to all files
map(raw_files_list, read_and_assign_simple)

Data cleaning

In this section, I want to remove any unnecessary rows and columns and rename the dataframes with something more intuitive.

I start by creating a tibble that matches each task/questionnaire identifier with a name.

identifier_names <- tribble(
  ~identifier, ~name,
  "svnz", "consent",
  "av22", "questionnaire_pre",
  "uamn", "go_nogo_m",
  "8o8a", "go_nogo_p",
  "yknh", "fake_news_game",
  "nn4b", "debrief"
)

identifier_names %>% 
  tt(theme = "striped")

tinytable_0cd48fpwsovgd5fuxtv5

identifier	name
svnz	consent
av22	questionnaire_pre
uamn	go_nogo_m
8o8a	go_nogo_p
yknh	fake_news_game
nn4b	debrief

Select, filter, and rename variables

Consent (svnz)

data_consent <- data_questionnaire_svnz %>% select(
  `Participant Private ID`,
  `UTC Date and Time`,
  `Experiment Version`,
  `Participant Device`,
  `Participant Browser`,
  `randomiser-evbs`,
  `attention_start object-14 Response`:`recontact object-19 Quantised`)

data_consent <- data_consent %>% 
  rename(
    consent1 = `Consent Form object-17 I confirm that I have read and understood the information sheet about the study.
-I Agree
`,
    consent2 = `Consent Form object-17 I understand that my participation is voluntary and that I am free to withdraw from the study at any time, without giving a reason.
-I Agree
`,
    consent3 = `Consent Form object-17 I agree for my (non-identifiable) data to be uploaded into a public depository for scientific purposes.
-I Agree
`,
    consent4 = `Consent Form object-17 I agree to take part in this study.
-I Agree
`,
    attention_start = `attention_start object-14 Response`,
    recontact = `recontact object-19 Response`
  )

Questionnaires (av22)

data_questionnaires <- data_questionnaire_av22 %>% 
  select(
    `Participant Private ID`,
    `age object-18 Month`:`dog11 object-131 Quantised`,
    -contains("Quantised"))

data_questionnaires <- data_questionnaires %>% 
  rename(age_month = `age object-18 Month`,
         age_year = `age object-18 Year`,
         gender = `gender object-6 Response`,
         gender_other = `gender object-6 Other`,
         worksit = `worksit object-19 Response`,
         worksit_other = `worksit object-19 Other`,
         education = `education object-11 Response`,
         education_other = `education object-11 Other`,
         ideology = `ideology object-38 Response`,
         partisanship = `partisanship object-23 Response`,
         partisanship_other = `partisanship object-23 Other`,
         conservative_rating = `conservative object-24 Value`,
         labour_rating = `labour object-27 Value`,
         libdem_rating = `libdem object-28 Value`,
         green_rating = `green object-29 Value`,
         reform_rating = `reform object-30 Value`,
         crt1 = `CRT1 object-31 Value`,
         crt2 = `CRT2 object-33 Value`,
         crt3 = `CRT3 object-35 Value`,
         o_immigration = `immigration object-91 Response`,
         o_climate = `climate object-92 Response`,
         o_punishment = `punishment object-93 Response`,
         o_teaculture = `teaculture object-94 Response`,
         o_brain = `brain object-96 Response`,
         attention_check = `attention object-97 Response`,
         o_discrimination = `discrimination object-107 Response`,
         o_cats = `cats object-108 Response`,
         o_selfenhancement = `selfenhancement object-109 Response`,
         o_adoption = `adoption object-110 Response`,
         o_gender = `gender object-111 Response`,
         dog01 = `dog01 object-112 Response`,
         dog02 = `dog02 object-113 Response`,
         dog03 = `dog03 object-114 Response`,
         dog04 = `dog04 object-115 Response`,
         dog05 = `dog05 object-116 Response`,
         dog06 = `dog06 object-117 Response`,
         dog07 = `dog07 object-127 Response`,
         dog08 = `dog08 object-128 Response`,
         dog09 = `dog09 object-129 Response`,
         dog10 = `dog10 object-130 Response`,
         dog11 = `dog11 object-131 Response`
         )

Go / No-Go M Start (uamn)

data_gng_m_sel <- data_task_uamn %>% 
  select(
    `Participant Private ID`,
    `UTC Date and Time`,
    `Experiment Version`,
    `Participant Device`,
    `Participant Browser`,
    `Task Name`,
    `randomiser-evbs`,
    `Event Index`,
    `Trial Number`,
    Screen,
    `Component Name`,
    `Object Name`,
    `Response Type`,
    Response,
    `Reaction Time`,
    Correct,
    `Spreadsheet: stimulus`:`Spreadsheet: trial_id`,
    Display,
  )

data_gng_m_sel <- data_gng_m_sel %>% 
  rename(
    response = Response,
    rt = `Reaction Time`,
    correct = Correct,
    stimulus = `Spreadsheet: response`,
    letter = `Spreadsheet: stimulus`,
    condition = Display,
    trial_id = `Spreadsheet: trial_id`,
  )

data_gng_m <- data_gng_m_sel %>% 
  filter(`Response Type` == "response")

Go / No-Go P Start (8o8a)

data_gng_p_sel <- data_task_8o8a %>% 
  select(
    `Participant Private ID`,
    `UTC Date and Time`,
    `Experiment Version`,
    `Participant Device`,
    `Participant Browser`,
    `Task Name`,
    `randomiser-evbs`,
    `Event Index`,
    `Trial Number`,
    Screen,
    `Component Name`,
    `Object Name`,
    `Response Type`,
    Response,
    `Reaction Time`,
    Correct,
    `Spreadsheet: stimulus`:`Spreadsheet: trial_id`,
    Display,
  )

data_gng_p_sel <- data_gng_p_sel %>% 
  rename(
    response = Response,
    rt = `Reaction Time`,
    correct = Correct,
    stimulus = `Spreadsheet: response`,
    letter = `Spreadsheet: stimulus`,
    condition = Display,
    trial_id = `Spreadsheet: trial_id`,
  )

data_gng_p <- data_gng_p_sel %>% 
  filter(`Response Type` == "response")

Fake News Game (yknh)

data_fake_news_sel <- data_task_yknh %>% 
  select(
    `Participant Private ID`,
    `UTC Date and Time`,
    `Experiment Version`,
    `Participant Device`,
    `Participant Browser`,
    `Task Name`,
    `Task Version`,
    `Trial Number`,
    Display,
    `Response Type`,
    `Component Name`,
    Screen,
    Tag,
    `Reaction Time`,
    `Spreadsheet: task`,
    `Spreadsheet: identifier`,
    `Spreadsheet: question`,
    `Spreadsheet: name`,
    `Spreadsheet: type`,
    Response,
    `Spreadsheet: message`,
    `Spreadsheet: correct_answer`,
    Correct,
    `Response Duration`,
  )

data_fake_news_sel <- data_fake_news_sel %>% 
  rename(rt = `Reaction Time`,
         trial_type = `Spreadsheet: task`,
         trial_id = `Spreadsheet: identifier`,
         question_type = `Spreadsheet: type`,
         question_topic = `Spreadsheet: name`,
         question = `Spreadsheet: question`,
         response = Response,
         message = `Spreadsheet: message`,
         correct_answer = `Spreadsheet: correct_answer`,
         guess_correct = Correct,
         response_duration = `Response Duration`
         )

data_fake_news <- data_fake_news_sel %>% 
  filter(`Response Type` == "response")

Debrief (nn4b)

data_debrief <- data_questionnaire_nn4b %>% 
  select(`Participant Private ID`,
         `attention_end object-3 Response`)

data_debrief <- data_debrief %>% 
  rename(
    attention_end = `attention_end object-3 Response`
  )

Join relevant data frames

dfs <- list(data_consent, data_questionnaires, data_debrief)

# join all dfs
data_questionnaires_combined <- 
  reduce(dfs, full_join, by = "Participant Private ID")

head(data_questionnaires_combined) %>% 
  tt()

tinytable_64uvhct1r2wsj896rho9

Participant Private ID	UTC Date and Time	Experiment Version	Participant Device	Participant Browser	randomiser-evbs	attention_start	attention_start object-14 Quantised	consent1	consent2	consent3	consent4	recontact	recontact object-19 Quantised	age_month	age_year	gender	gender_other	worksit	worksit_other	education	education_other	ideology	partisanship	partisanship_other	conservative_rating	labour_rating	libdem_rating	green_rating	reform_rating	crt1	crt2	crt3	o_immigration	o_climate	o_punishment	o_teaculture	o_brain	attention_check	o_discrimination	o_cats	o_selfenhancement	o_adoption	o_gender	dog01	dog02	dog03	dog04	dog05	dog06	dog07	dog08	dog09	dog10	dog11	attention_end
11693545	12/09/2024 08:16:23	38	Desktop or Laptop	Chrome 130.0.0.0	Start P	Yes	1	1	1	1	1	Yes	1	0	39	male	NA	Employed	NA	Higher secondary or further education (A-levels, T-levels, BTEC, International Baccalaureate or equivalent)	NA	Left	Labour	NA	3	91	43	84	1	8	10	39	Strongly disagree	Strongly agree	Disagree	Neutral	Neutral	Strongly agree	Strongly agree	Disagree	Agree	Strongly agree	Strongly disagree	Disagree	Strongly agree	Strongly disagree	Strongly agree	Agree	Disagree	Agree	Agree	Strongly agree	Strongly disagree	Disagree	Yes
11693585	12/09/2024 08:21:22	38	Desktop or Laptop	Chrome 128.0.0.0	Start M	Yes	1	1	1	1	1	Yes	1	9	36	female	NA	Employed	NA	Higher secondary or further education (A-levels, T-levels, BTEC, International Baccalaureate or equivalent)	NA	Right	Conservative	NA	94	0	0	10	91	8	50	80	Neutral	Neutral	Agree	Agree	Neutral	Strongly agree	Neutral	Agree	Agree	Agree	Disagree	Disagree	Agree	Disagree	Agree	Agree	Disagree	Agree	Agree	Agree	Disagree	Neutral	Yes
11693590	12/09/2024 08:21:53	38	Desktop or Laptop	Chrome 128.0.0.0	Start P	Yes	1	1	1	1	1	Yes	1	0	32	male	NA	Self-employed	NA	Bachelors degree (BA, BSc., BEd., BEng.)	NA	Left	Green	NA	5	20	30	85	0	4	50	39	Strongly disagree	Strongly agree	Strongly disagree	Agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Disagree	Strongly agree	Strongly disagree	Disagree	Strongly agree	Strongly disagree	Strongly agree	Strongly agree	Disagree	Strongly agree	Strongly agree	Strongly agree	Strongly disagree	Disagree	Yes
11693627	12/09/2024 08:27:29	38	Desktop or Laptop	Chrome 128.0.0.0	Start P	Yes	1	1	1	1	1	Yes	1	1	36	female	NA	Employed	NA	Bachelors degree (BA, BSc., BEd., BEng.)	NA	Left	Labour	NA	27	89	23	35	2	8	50	20	Strongly disagree	Strongly agree	Disagree	Neutral	Neutral	Strongly agree	Strongly agree	Agree	Agree	Strongly agree	Strongly disagree	Disagree	Strongly agree	Disagree	Agree	Agree	Disagree	Agree	Strongly agree	Strongly agree	Disagree	Disagree	Yes
11693677	12/09/2024 08:39:20	38	Desktop or Laptop	Chrome 128.0.0.0	Start M	Yes	1	1	1	1	1	Yes	1	6	37	female	NA	Employed	NA	Higher secondary or further education (A-levels, T-levels, BTEC, International Baccalaureate or equivalent)	NA	Right	Reform UK	NA	0	0	1	0	75	8	50	20	Strongly agree	Neutral	Disagree	Strongly agree	Agree	Strongly agree	Neutral	Agree	Agree	Agree	Disagree	Disagree	Neutral	Strongly disagree	Strongly agree	Strongly agree	Strongly disagree	Strongly agree	Strongly agree	Strongly agree	Disagree	Neutral	Yes
11693689	12/09/2024 08:39:33	38	Desktop or Laptop	Chrome 128.0.0.0	Start M	Yes	1	1	1	1	1	Yes	1	6	35	male	NA	Employed	NA	Bachelors degree (BA, BSc., BEd., BEng.)	NA	Slightly right	Conservative	NA	60	15	42	12	10	8	2	39	Neutral	Agree	Neutral	Neutral	Disagree	Disagree	Agree	Disagree	Disagree	Disagree	Neutral	Disagree	Agree	Disagree	Agree	Agree	Disagree	Agree	Agree	Agree	Neutral	Neutral	Yes

data_gng <- bind_rows(data_gng_m, data_gng_p)

head(data_gng) %>% 
  tt()

tinytable_achk4ujh27i9ebyvx0c6

Participant Private ID	UTC Date and Time	Experiment Version	Participant Device	Participant Browser	Task Name	randomiser-evbs	Event Index	Trial Number	Screen	Component Name	Object Name	Response Type	response	rt	correct	letter	stimulus	trial_id	condition
11693585	12/09/2024 08:28:20	38	Desktop or Laptop	Chrome 128.0.0.0	Go / No-Go Task (M condition)	Start M	7	1	Stimulus	Keyboard Response	go	response	go	450	1	M	go	practice_006	Practice M
11693585	12/09/2024 08:28:21	38	Desktop or Laptop	Chrome 128.0.0.0	Go / No-Go Task (M condition)	Start M	10	2	Stimulus	Keyboard Response	go	response	go	500	1	M	go	practice_008	Practice M
11693585	12/09/2024 08:28:23	38	Desktop or Laptop	Chrome 128.0.0.0	Go / No-Go Task (M condition)	Start M	13	3	Stimulus	Time Limit	screen	response	nogo	500	1	W	nogo	practice_009	Practice M
11693585	12/09/2024 08:28:24	38	Desktop or Laptop	Chrome 128.0.0.0	Go / No-Go Task (M condition)	Start M	16	4	Stimulus	Keyboard Response	go	response	go	392	1	M	go	practice_004	Practice M
11693585	12/09/2024 08:28:26	38	Desktop or Laptop	Chrome 128.0.0.0	Go / No-Go Task (M condition)	Start M	19	5	Stimulus	Time Limit	screen	response	nogo	500	1	W	nogo	practice_010	Practice M
11693585	12/09/2024 08:28:27	38	Desktop or Laptop	Chrome 128.0.0.0	Go / No-Go Task (M condition)	Start M	22	6	Stimulus	Keyboard Response	go	response	go	364	1	M	go	practice_007	Practice M

Remove participants who failed attention check

As pre-registered, I remove participants who failed a very obvious attention check right at the beginning of the study. One participant had to be removed due to ethical reasons as they incorrectly indicated their age on Prolific.

data_questionnaires %>% 
  filter(attention_check != "Strongly agree") %>% 
  select(`Participant Private ID`, age_year, ideology) %>% 
  tt()

tinytable_lt9w6on1z7dggfvo2d88

Participant Private ID	age_year	ideology
11693689	35	Slightly right
11700313	24	Slightly right

data_gng_f <- data_gng %>% 
  filter(!(`Participant Private ID` %in% c(11693689, 11700313)))

data_fake_news_f <- data_fake_news %>% 
  filter(!(`Participant Private ID` %in% c(11693689, 11700313)))

data_questionnaires_combined_f <- data_questionnaires_combined %>% 
  filter(!(`Participant Private ID` %in% c(11693689, 11700313)))

Check technical errors

data_questionnaires_combined %>%
  count(`Participant Private ID`) %>% 
  filter(n != 1)

# A tibble: 0 × 2
# ℹ 2 variables: Participant Private ID <dbl>, n <int>

The questionnaires look good.

data_gng %>% 
  count(`Participant Private ID`) %>% 
  filter(n != 300)

# A tibble: 2 × 2
  `Participant Private ID`     n
                     <dbl> <int>
1                 11694557   450
2                 11695853   296

For some reason two IDs have not 300 observations which should not happen and is a technical error from Gorilla. As the study was set up, it is not possible to have less or more than 300 trials, and this thus an indication that there was an error and data cannot be used.

data_fake_news %>% 
  count(`Participant Private ID`) %>% 
  filter(n > 35 | n < 25)

# A tibble: 2 × 2
  `Participant Private ID`     n
                     <dbl> <int>
1                 11694792    55
2                 11696062    55

Another two participants have a weird number of observations and need to be removed. This should not happen and again is a technical issue from Gorilla.

Remove technical errors

This was not pre-registered, as technical errors outside of the control of the researchers cannot be.

data_gng_f <- data_gng_f %>% 
  filter(!(`Participant Private ID` %in% c(11694557, 11695853, 
                                           11694792, 11696062)))

data_fake_news_f <- data_fake_news_f %>% 
  filter(!(`Participant Private ID` %in% c(11694557, 11695853, 
                                           11694792, 11696062)))

data_questionnaires_combined_f <- data_questionnaires_combined_f %>% 
  filter(!(`Participant Private ID` %in% c(11694557, 11695853, 
                                           11694792, 11696062)))

Check the age of participants

I intended to recruit only 18-38 year olds - we expect some deviation as this is based on Prolific and not all information is always up to date. Let’s check if there are some participants that incorrectly stated their age.

data_questionnaires_combined_f %>% 
  filter(age_year < 18 | age_year > 38) %>% 
  select(`Participant Private ID`, age_year)

# A tibble: 7 × 2
  `Participant Private ID` age_year
                     <dbl> <chr>   
1                 11693545 39      
2                 11694382 NaN     
3                 11694592 40      
4                 11694730 39      
5                 11694907 39      
6                 11695000 51      
7                 11695048 124

I am not super concered about the participants who are slightly above 38. However, the others, I contacted on Prolific. Two of them could correct their age and reported the following ages:

11695048 –> 38
11694382 -> 38

So let’s create a age variable that takes the age in years for all participants, but for these two uses the corrected values.

data_questionnaires_combined_f <- data_questionnaires_combined_f %>%
  mutate(age_year = as.numeric(age_year)) %>% 
  mutate(age_corrected = case_when(
    `Participant Private ID` == 11695048 ~ 38,
    `Participant Private ID` == 11694382 ~ 38,
    TRUE ~ age_year  
  ))

Demographics of filtered participants

data_questionnaires_combined %>% 
  filter(`Participant Private ID` %in% c(11693689, 11700313,
                                         11694557, 11695853, 
                                         11694792, 11696062)) %>% 
  select(`Participant Private ID`, `Participant Browser`, ideology,
         age_year) %>% 
  tt()

tinytable_i8lq7i6pf7mkfusq9jhf

Participant Private ID	Participant Browser	ideology	age_year
11693689	Chrome 128.0.0.0	Slightly right	35
11694557	Edge 128.0.0.0	Slightly left	32
11694792	Firefox 130.0	Slightly left	33
11696062	Chrome 128.0.0.0	Right	16
11700313	Chrome 128.0.0.0	Slightly right	24
11695853	Mobile Safari 17.6	Slightly right	34

This leaves us with the final pre-registered sample size of exactly N = 504 participants.

Save dataframes

Save different .csv data frames for further analyses.

# questionnaire data
write_csv(data_questionnaires_combined_f, here("01_data", "cleaned", "data_questionnaires_cleaned.csv"), 
          na = "", append = FALSE, col_names = TRUE)

# gng data
write_csv(data_gng_f, here("01_data", "cleaned", "data_gng_cleaned.csv"), 
          na = "", append = FALSE, col_names = TRUE)

# fake news task data
write_csv(data_fake_news_f, here("01_data", "cleaned", "data_fake_news_cleaned.csv"), 
          na = "", append = FALSE, col_names = TRUE)